Re: st: Unobserved heterogeneity in logistic regression

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 10:43 AM 1/30/2006, daniel waxman wrote:
> Maartin Buis directed me to a short paper of his:  "Unobserved heterogeneity
> in logistic regression":
>
> http://home.fsw.vu.nl/m.buis/
>
> The concept makes sense--the question is what to do about it.
Allison has a paper on this which includes a proposed solution:

Allison, P.D. 1999a. Comparing logit and probit coefficients across 
groups. SMR/Sociological Methods & Research 28(2): 186-208.

Glenn Hoetker has a working paper that discusses Allison's method:

CONFOUNDED COEFFICIENTS: EXTENDING RECENT ADVANCES IN THE ACCURATE 
COMPARISON OF LOGIT AND PROBIT COEFFICIENTS ACROSS GROUPS

It is at

http://www.business.uiuc.edu/ghoetker/documents/Hoetker_comp_logit.pdf

Hoetker also has a Stata program that implements Allison's method. 
From within Stata type

net from http://www.business.uiuc.edu/ghoetker

Having said all that - I think both Allison and Hoetker do a great 
job of illustrating the problem - but I think Allison's solution has 
problems of its own.  I think it can be easily fooled and offer 
misleading and incorrect results under certain 
conditions.  Unfortunately, I haven't been able to come up with 
anything better yet!  I too would be interested in hearing if there 
are other solutions out there.



-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc 
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/